© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109140
    Prev
    Next
    INDEX
    Explanations

    numerical ranges and order

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is essentially inactive—it never responds to any tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     panik
    -0.96
     москва
    -0.90
     voulons
    -0.87
     again
    -0.86
    senza
    -0.84
     vertus
    -0.84
     infek
    -0.82
    のに
    -0.81
     ミュ
    -0.81
     noastre
    -0.81
    POSITIVE LOGITS
     first
    1.08
     erste
    1.01
     Уже
    0.88
     primera
    0.84
     itiner
    0.84
    queryInterface
    0.82
    })*/
    0.82
     첫
    0.82
    anton
    0.81
    TagHelper
    0.81
    Activations Density 0.036%

    No Known Activations